Amazon Customer Review & Rating Summary Scraper: MCP config, n8n workflow and API

{
  "productUrls": [
    "https://www.amazon.com/dp/B09X7MPX8L"
  ],
  "maxProductsToDiscover": 5,
  "country": "amazon.com",
  "maxReviews": 15,
  "extendedHistory": true,
  "sortBy": "helpful",
  "verifiedPurchasesOnly": false,
  "mediaReviewsOnly": false,
  "includeImages": true,
  "includeAggregates": true,
  "includeGdprSensitive": false
}

---
name: amazon-customer-review-and-rating-summary-scraper
description: "One record per Amazon customer review (rating, text, verified/Vine flags, helpful votes, variant, media, dates, source metadata) plus one type=amazon_review_aggregate record per product with the rating summary and star histogram. Empty fields are omitted, never pushed as null. Runs the Apify Actor vexaloom-labs/amazon-customer-review-and-rating-summary-scraper. Use when the user needs Amazon data with fields such as productAsin, ratingScore, reviewTitle, reviewDescription, isVerified, reviewedIn and an Apify token is available."
compatibility: "Needs network access, curl, and an APIFY_TOKEN environment variable. Runs are billed to the token owner's Apify account."
metadata:
  actor: "vexaloom-labs/amazon-customer-review-and-rating-summary-scraper"
  store-url: "https://apify.com/vexaloom-labs/amazon-customer-review-and-rating-summary-scraper"
---

# Amazon Customer Review & Rating Summary Scraper

Use this skill to fetch Amazon data with the Apify Actor `vexaloom-labs/amazon-customer-review-and-rating-summary-scraper` and work with the returned rows.

## Before running

1. Check that `APIFY_TOKEN` is set in the environment. Never print it or write it to a file.
2. Build `input.json` from the user's request using the fields below. Keep limits small for a first run.
3. Confirm the search terms or URLs with the user if the request is ambiguous.

## Input fields

| Field | Type | Meaning |
| --- | --- | --- |
| `productUrls` | array | Amazon product URLs (/dp/, /gp/product/, /gp/aw/d/, /product/) or bare 10-character ASINs, on any supported Amazon domain. Leave empty to discover products from `keywords`/`categoryUrls` instead. |
| `keywords` | array | Search terms used to discover products when `productUrls` is empty (e.g. "wireless earbuds"). Each keyword contributes up to `maxProductsToDiscover` products. |
| `categoryUrls` | array | Advanced discovery: Amazon `/s?...` search URLs or `/b?node=...` category URLs. Used only when `productUrls` is empty. |
| `maxProductsToDiscover` | integer | Maximum products discovered from each keyword or category URL (1-50). Ignored when `productUrls` is supplied. |
| `country` | string | Amazon storefront to use for bare ASINs, discovery, and products whose URL does not carry a domain. Product URLs keep their own domain. |
| `maxReviews` | integer | Hard cap per product after merging and deduplication (1-2000). The product-page sample alone yields about 8-13 rows; the optional extended feed can add 100-800+ for popular US products. In optional cookie mode this is the paginated cap. |
| `extendedHistory` | boolean | Merge Amazon's public extended review feed for each ASIN (no login): up to 100 rows per star/sort bucket, typically 100-800+ unique reviews for popular US products, deduplicated against the product-page sample. |
| `mergeMarketplaces` | array | Fetch the same product on these additional Amazon marketplaces and merge their deduplicated product-page reviews. Empty = the product's own marketplace only. |
| `sortBy` | one of `helpful`, `recent` | Order of the returned reviews: most helpful first, or most recent first. |
| `verifiedPurchasesOnly` | boolean | Keep only reviews carrying Amazon's Verified Purchase badge. Applied server-side in the extended feed (and cookie mode) and client-side for product-page rows. |
| `filterKeywords` | array | Keep only reviews whose title or text contains at least one of these keywords (case-insensitive). Empty = no keyword filter. |
| `reviewsNewerThan` | string | Keep only reviews dated on or after this date (YYYY-MM-DD or any ISO date). Reviews whose localized date cannot be parsed are kept. Empty = no date filter. |
| `mediaReviewsOnly` | boolean | Keep only reviews that include at least one reviewer-uploaded image or video. |
| `includeImages` | boolean | Extract full-resolution image and video URLs uploaded by reviewers. |

Example `input.json` (the Actor's published prefill):

```json
{
  "productUrls": [
    "https://www.amazon.com/dp/B09X7MPX8L"
  ],
  "maxProductsToDiscover": 5,
  "country": "amazon.com",
  "maxReviews": 15,
  "extendedHistory": true,
  "sortBy": "helpful",
  "verifiedPurchasesOnly": false,
  "mediaReviewsOnly": false,
  "includeImages": true,
  "includeAggregates": true,
  "includeGdprSensitive": false
}
```

## Run

```bash
curl -sS -X POST "https://api.apify.com/v2/acts/vexaloom-labs~amazon-customer-review-and-rating-summary-scraper/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d @input.json > results.json
```

The call waits for the run to finish and returns the dataset items as a JSON array. If the run needs more than 300 seconds the API answers with HTTP 408; then start the run with `POST /v2/acts/vexaloom-labs~amazon-customer-review-and-rating-summary-scraper/runs`, poll `GET /v2/actor-runs/{runId}` until `SUCCEEDED`, and read `GET /v2/datasets/{defaultDatasetId}/items`.

## Output

Each item is one record. Published fields include: `productAsin`, `ratingScore`, `reviewTitle`, `reviewDescription`, `isVerified`, `reviewedIn`, `reviewReaction`, `variant`, `reviewImages`, `position`, `reviewId`, `helpfulCount`, `reviewDate`, `reviewLocation`, `sentimentHint`, `wordCount`, `hasImages`, `imageCount`, `scrapedAt`, `sourceUrl`.

Summarise what was found, cite the record URLs when present, and say how many items came back. Do not invent values for empty fields.